Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4790 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1324283 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1044281 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3245. Min Act: -0.0000

Data Index: 389769 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3440. Min Act: -0.0000

Data Index: 766628 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3611. Min Act: -0.0000

Data Index: 214991 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2876. Min Act: -0.0000

Data Index: 261144 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2717. Min Act: -0.0000

Data Index: 882860 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2873. Min Act: -0.0000

Data Index: 884488 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2662. Min Act: -0.0000

Data Index: 709172 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2870. Min Act: -0.0000

Data Index: 356324 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1237777 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2480. Min Act: -0.0000

Data Index: 877382 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1136618 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1218988 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1101003 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2345. Min Act: -0.0000

Data Index: 528970 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1330906 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2588. Min Act: -0.0000

Data Index: 201503 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2495. Min Act: -0.0000

Data Index: 693798 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1332419 (C4 (Web Text))

Max Activating Token Index: 144